{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import torch\n", "import mediapy as media\n", "from mattport.nerf.field_modules import encoding\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# NeRF Positional Encoding\n", "First introduced in the original NeRF paper. This encoding assumes the inputs are between zero and one and can opperate on any dimensional input." ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Input Values:\n" ] }, { "data": { "text/html": [ "
" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "Encoded Values:\n" ] }, { "data": { "text/html": [ "
" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "num_frequencies = 4\n", "min_freq_exp = 0\n", "max_freq_exp = 6\n", "include_input = True\n", "resolution = 128\n", "\n", "encoder = encoding.NeRFEncoding(\n", " in_dim=2,\n", " num_frequencies=num_frequencies,\n", " min_freq_exp=min_freq_exp,\n", " max_freq_exp=max_freq_exp,\n", " include_input=include_input,\n", ")\n", "\n", "x_samples = torch.linspace(0, 1, resolution)\n", "grid = torch.stack(torch.meshgrid([x_samples, x_samples], indexing=\"ij\"), dim=-1)\n", "\n", "encoded_values = encoder(grid)\n", "\n", "print(\"Input Values:\")\n", "media.show_images(torch.moveaxis(grid, 2, 0), cmap=\"plasma\", border=True)\n", "print(\"Encoded Values:\")\n", "media.show_images(torch.moveaxis(encoded_values, 2, 0), cmap=\"plasma\", border=True)\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Random Fourier Feature (RFF) Encoding\n", "This encoding assumes the inputs are between zero and one and can opperate on any dimensional input." ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Input Values:\n" ] }, { "data": { "text/html": [ "
" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "Encoded Values:\n" ] }, { "data": { "text/html": [ "
" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "num_frequencies = 8\n", "scale = 10\n", "resolution = 128\n", "\n", "encoder = encoding.RFFEncoding(in_dim=2, num_frequencies=num_frequencies, scale=scale)\n", "\n", "x_samples = torch.linspace(0, 1, resolution)\n", "grid = torch.stack(torch.meshgrid([x_samples, x_samples], indexing=\"ij\"), dim=-1)\n", "\n", "encoded_values = encoder(grid)\n", "\n", "print(\"Input Values:\")\n", "media.show_images(torch.moveaxis(grid, 2, 0), cmap=\"plasma\", border=True)\n", "print(\"Encoded Values:\")\n", "media.show_images(torch.moveaxis(encoded_values, 2, 0), cmap=\"plasma\", border=True)\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Hash Encoding\n", "The hash incoding was originally introduced in Instant-NGP. The encoding is optimized during training. This is a visualization of the initialization." ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Input Values:\n" ] }, { "data": { "text/html": [ "
" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "Encoded Values:\n" ] }, { "data": { "text/html": [ "
" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "num_levels = 8\n", "min_res = 2\n", "max_res = 128\n", "hash_table_size = 2**4 # Typically much larger tables are used\n", "\n", "resolution = 128\n", "slice = 0\n", "\n", "# Fixing features_per_level to 3 for easy RGB visualization. Typical value is 2 in networks\n", "features_per_level = 3\n", "\n", "encoder = encoding.HashEncoding(\n", " num_levels=num_levels,\n", " min_res=min_res,\n", " max_res=max_res,\n", " hash_table_size=hash_table_size,\n", " features_per_level=features_per_level,\n", " hash_init_scale=0.001,\n", ")\n", "\n", "x_samples = torch.linspace(0, 1, resolution)\n", "grid = torch.stack(torch.meshgrid([x_samples, x_samples, x_samples], indexing=\"ij\"), dim=-1)\n", "\n", "encoded_values = encoder(grid)\n", "\n", "grid_slice = grid[slice, ...]\n", "encoded_values_slice = encoded_values[slice, ...]\n", "\n", "print(\"Input Values:\")\n", "media.show_images(torch.moveaxis(grid_slice, 2, 0), cmap=\"plasma\", border=True)\n", "\n", "print(\"Encoded Values:\")\n", "encoded_images = encoded_values_slice.view(resolution, resolution, num_levels, 3)\n", "encoded_images = torch.moveaxis(encoded_images, 2, 0)\n", "encoded_images -= torch.min(encoded_images)\n", "encoded_images /= torch.max(encoded_images)\n", "media.show_images(encoded_images.detach().numpy(), cmap=\"plasma\", border=True)\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "interpreter": { "hash": "024fe9dea615e4e34961116ff517c7e9f5910440e3d2c8eb4560299f11aaf2e7" }, "kernelspec": { "display_name": "Python 3.9.11 ('mattport')", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.9.11" }, "orig_nbformat": 4 }, "nbformat": 4, "nbformat_minor": 2 }